Adaptive baseband predistorter for radio frequency power amplifiers based on a multilayer perceptron

Naskas, N; Papananos, Y

dc.contributor.author	Naskas, N	en
dc.contributor.author	Papananos, Y	en
dc.date.accessioned	2014-03-01T02:42:04Z
dc.date.available	2014-03-01T02:42:04Z
dc.date.issued	2002	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/30756
dc.subject	backpropagation	en
dc.subject	Mlp Neural Network	en
dc.subject	Multilayer Perceptron	en
dc.subject	Power Amplifier	en
dc.subject	Radio Frequency	en
dc.subject	Rf Power Amplifier	en
dc.subject	System Performance	en
dc.subject.other	Baseband predistorter	en
dc.subject.other	Digital baseband predistortion	en
dc.subject.other	Linearisation	en
dc.subject.other	Multi layer perceptron	en
dc.subject.other	Multilayer perceptron neural networks	en
dc.subject.other	Nonlinearities	en
dc.subject.other	Performance error	en
dc.subject.other	Radio frequency power	en
dc.subject.other	Radio frequency power amplifiers	en
dc.subject.other	Simulation result	en
dc.subject.other	Single input	en
dc.subject.other	Backpropagation algorithms	en
dc.subject.other	Multilayers	en
dc.subject.other	Neural networks	en
dc.subject.other	Power amplifiers	en
dc.subject.other	Radio	en
dc.subject.other	Radio waves	en
dc.subject.other	Radio frequency amplifiers	en
dc.title	Adaptive baseband predistorter for radio frequency power amplifiers based on a multilayer perceptron	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ICECS.2002.1046445	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ICECS.2002.1046445	en
heal.identifier.secondary	1046445	en
heal.publicationDate	2002	en
heal.abstract	A radio frequency (RF) power amplifier (PA) linearisation method based on a multilayer perceptron (MLP) neural network w) is presented. The proposed method is an alternative to digital baseband predistortion. In this case, a MLP with a single input and dual output is capable of compensating the amplitude-to-amplitude (AM/AM) and amplitude-to-phase (AM/PM) modulation that PA introduces. In order for this to be achieved the MLP is trained using a part of the down-converted response and a variant in the performance error of the backpropagation (BP) algorithm. After the first time training, the system can be retrained so as to adaptively compensate condition variations. The derived simulation results reveal the system performance in the PA's non-linearities. © 2002 IEEE.	en
heal.journalName	Proceedings of the IEEE International Conference on Electronics, Circuits, and Systems	en
dc.identifier.doi	10.1109/ICECS.2002.1046445	en
dc.identifier.volume	3	en
dc.identifier.spage	1107	en
dc.identifier.epage	1110	en